Policies section
New settings: two new dropdowns are under Policies in Manage Business:
Name shown on Terms & Privacy: NextChair, My business name, or NextChair and my business name.
Contact email on Terms & Privacy: NextChair (info@next-chair.co.uk) or My business email.
Fallbacks: both default to NextChair. If you pick the business email but haven’t set one, the form warns you and the pages fall back to the NextChair address.
Where the name appears: the choice changes the name in the header link, footer, “we/us” definition, privacy controller line and intro on both pages.
Business email: it replaces the address in the complaints section and the privacy contact lines.
Database change: this needed a new migration, 20261017120000_add_legal_display_settings. Existing businesses default to NextChair, so nothing changes for them. Run prisma migrate deploy on your server.
Terms and placeholders
Sections 15 (Governing law) and 16 (Contact us) are removed from terms/page.tsx, so the Terms now have 14 sections.
The [LEGAL ENTITY NAME] and [REGISTERED ADDRESS] placeholders are gone, along with the unused governing-law setting. The contact email is now info@next-chair.co.uk in legal-config.ts.
Login page
sign-in-form.tsx now shows “By continuing, you agree to our Terms of Service and Privacy Policy”, with both as links.
1. Pre-launch review (no code)
Listed what’s left before going live: testing, backups, monitoring, legal/GDPR, and a dry run on the VPS.
Listed the features a barbershop system usually has and which of them you’re missing.
Researched WhatsApp pricing, which led to the free route below.
2. Security cleanup
This came out of that review.
Deleted: /dev/scheduling-test (a test page that shipped), /api/debug/db-connect-test (a leftover debug route), and two files of unauthenticated booking and appointment actions (11 actions). One of them listed appointments with customer details to anyone.
Audited: all 127 server actions. The only unguarded ones left are the intended public ones: availability lookups, cookie-based booking drafts, and the token-gated one-time installer.
Tidied: removed the four now-dead booking schemas from schemas.ts.
3. Client import from a spreadsheet
Entry points: an upload icon next to “+” on the Clients page, and a link on the Add Client page. It’s owner-only, checked again on the server.
Flow: /staff/clients/import.
Upload a CSV and check the guessed column mapping.
Review the preview, then import in chunks with progress.
A report lists problem rows by spreadsheet row number, with a download.
CSV template: a visible “Download CSV template” button (headers only: First name, Last name, Email, Phone).
Behavior:
Each client gets a sign-in-ready account, the same as adding one by hand.
Nobody is emailed.
Existing emails are left untouched.
Earlier guest bookings under the same email attach automatically.
“Surname, Firstname” names are read the right way round.
People sharing a phone number still import.
Limits: an email is required for every row, CSV only (no .xlsx), up to 5,000 rows per file, and notes aren’t imported.
4. WhatsApp reminders (free, manual route)
Button: a WhatsApp button next to Call and Email on four pages: the owner and barber appointment pages, “Current appointment”, and the client page. It opens WhatsApp with a ready-written reminder, including a “change it” link.
Phone numbers: read as the business’s own country when typed without a country code. This uses the new libphonenumber-js dependency. A number WhatsApp can’t use means no button.
Reminders list: a new /staff/reminders page lists tomorrow’s confirmed bookings in time order.
Each row has a one-tap Send on WhatsApp.
Tapping marks it “Sent 14:46”, with an Undo.
The mark shows on the appointment pages too.
Barbers see their own list; owners see the whole shop with barber names.
Calendar link: “WhatsApp reminders · 3 to send tomorrow” on both calendar pages.
Database: one additive migration, Appointment.whatsappReminderSentAt. Rescheduling clears it, since a reminder for the old time says nothing about the new one.
Audit log: who marked or undid each reminder is recorded.
Tests and verification
Before today Now
Unit tests 297 331
Integration tests 273 285
New unit tests: the CSV parser, import row logic, and WhatsApp link and phone handling.
New integration tests: the import service and the reminders service.
Checks: typecheck and lint are clean (the one old branding warning remains).
Browser: I exercised each feature in a real browser against a throwaway MySQL 8, including the permission split between Leo and Marcus.
Core logic: types.ts (defaults), notification.service.ts (skipEmail + dedup), booking-notifications.ts, loyalty-notifications.ts, reminder-scheduling.ts, booking.service.ts + scheduling.service.ts (staff-selection capture), features/owner/actions/appointments.ts.
Schema: prisma/schema.prisma + new migration 20260912165903_add_staff_selected_by_customer.
UI: both notification-preferences pages (customer, staff) now use the same default logic as the actual send decision.
Tests: notification.service.integration.test.ts, booking-notifications.integration.test.ts, reminder-scheduling.integration.test.ts, loyalty-notifications.integration.test.ts, plus a new createTestAppointment fixture.
Docs: docs/notifications.md rewritten to match.
Default changes
Exactly as specified — full table is in docs/notifications.md. In short: STAFF_NEW_APPOINTMENT, STAFF_APPOINTMENT_RESCHEDULED, STAFF_APPOINTMENT_REMINDER, OWNER_NEW_BOOKING, OWNER_NO_SHOW now default off; everything else that was already toggleable is untouched.
No longer email (fixed, not a toggle)
BOOKING_COMPLETED, LOYALTY_STAMP_ADDED, LOYALTY_REWARD_REDEEMED — always. BOOKING_BARBER_CHANGED — only when the customer originally booked "any available barber." The customer's 2-hour reminder is removed entirely (24h stays); staff keeps both, just off by default. All via a new skipEmail flag on notify(), checked in one place — no new preference rows for these.
Deduplication
One new EQUIVALENCE_GROUPS map in notification.service.ts (STAFF_NEW_APPOINTMENT>OWNER_NEW_BOOKING, STAFF_APPOINTMENT_CANCELLED>OWNER_BOOKING_CANCELLED). Inside notify(), before creating deliveries, it checks for an already-created equivalent notification for the same (businessId, appointmentId, recipientUserId); if found and at-least-as-relevant, the new one gets zero deliveries on every channel (row still created for audit trail). Only listed types participate, so OWNER_NO_SHOW and any future actionable owner type are never touched.
1. Summary of changes
Password auth → email OTP, everywhere it existed for the tenant/business app: sign-in, customer self-registration (/register), staff-invitation acceptance, and the installer's administrator step. Flow is always: email → 6-digit code emailed → code entered → session created, via one shared service (otp.service.ts) reused by every entry point.
NextChair Manager's own auth was not touched — this only affects tenant-side (business admin/staff/customer) authentication, per the spec's explicit instruction.
Installer improvements: Step 2 (Administrator) now asks only Name + Email + optional Phone, verified inline via the same OTP widget (no redirect). Step 3 (Business Details) pre-fills Business Name from the Manager-provisioned BUSINESS_NAME, shows the booking URL (NEXT_PUBLIC_APP_URL) as a read-only info box instead of asking for it, and has a distinctly-labeled "Business Website (optional)" field with copy clarifying it's not the booking URL.
Installation cannot complete with an unverified admin email — enforced server-side (finalizeOtp runs inside the same DB transaction as user/business creation), not just trusted from client state. A mid-wizard refresh still can't create duplicate admins or partial records — that property was preserved by design, not incidentally.
2. Prisma/database changes
New EmailOtp model (email as PK — one row per address, so a new request naturally invalidates the previous code): codeHash, purpose, expiresAt, attempts, verifiedAt, consumedAt, timestamps. Only a bcrypt hash of the code is ever stored.
User.passwordHash — unchanged schema (already nullable), just annotated as deprecated. No destructive migration; historical rows are untouched.
Migration: prisma/migrations/20260905190022_email_otp_authentication — adds EmailOtp only. Generated and applied against throwaway containers only; the real next-chair-mysql production database was never touched (confirmed not even running on this host during this session).
3. New environment variables
None required for production. One new variable, E2E_TEST_MODE, exists purely for the Playwright suite (set only in playwright.config.ts's webServer.env) — it unlocks a /api/test/otp-code debug endpoint and bypasses OTP rate limiting so the same seeded users can sign in dozens of times across one test run. It must never be set on a real deployment; nothing in the app sets it anywhere else.
4. Email delivery configuration
Nothing new to configure. OTP emails reuse the existing EmailProvider abstraction and EMAIL_PROVIDER env var exactly as configured today — console in dev (prints to server logs), brevo in production via the same SMTP credentials already documented. The OTP email is a new template (otp-email.ts) sent directly (bypassing the async notification/cron pipeline, since a 10-minute-expiry code can't wait for a delivery retry loop).
5. Migration considerations for existing users/installations
Existing users lose password sign-in — the only way to authenticate now is email OTP. There is no in-app fallback; this is an intentional, sharp cutover. If existing customers/staff/admins need advance notice, that's a business/communications decision outside this change.
No account data is deleted or migrated — passwordHash rows are simply never read for auth anymore.
prisma/seed.ts / scripts/ensure-super-admin.ts still set a passwordHash for seeded dev users — harmless and vestigial now, not cleaned up (flagging it rather than touching seed data silently).
Installations already completed are unaffected; only new installer runs go through the OTP admin-verification step.
6. Files changed
New:
src/lib/auth/otp.service.ts — the core requestOtp/verifyOtp/finalizeOtp service
src/lib/auth/__tests__/otp.service.integration.test.ts
src/services/notifications/templates/otp-email.ts
src/features/auth/components/otp-code-step.tsx — shared code-entry UI
src/features/auth/actions/request-sign-in-otp.ts
src/app/api/test/otp-code/route.ts — e2e-only, gated on E2E_TEST_MODE
prisma/migrations/20260905190022_email_otp_authentication/
Modified — auth core: prisma/schema.prisma, src/auth.ts, src/features/auth/schemas.ts
Modified — sign-in/register/invitations: sign-in-form.tsx, register.ts, register-form.tsx, accept-invitation.ts, accept-invitation-form.tsx, staff-invitation.service.ts
Modified — installer: installer.service.ts, schema.ts, install.ts, install-wizard.tsx, install/page.tsx, installer.service.integration.test.ts
Modified — email / e2e infra: console-email-provider.ts, playwright.config.ts, e2e/helpers.ts, and the four e2e/*.spec.ts files (dropped the now-unused password argument from every signIn() call).
7. Verification performed
npx tsc --noEmit, npm run lint, npm test (276 unit) — all clean.
npm run test:integration (207 tests, throwaway DB) — includes 11 new OTP-service tests and a rewritten installer suite; a genuine race condition in requestOtp (concurrent requests for a brand-new email double-hitting the upsert's create branch) was caught and fixed here.
Full npm run test:e2e against a fresh throwaway database: 36/37 passed. The one failure (owner-journeys "opening hours conflict" test) is a pre-existing, auth-unrelated ordering flake — appointment-count ambiguity from earlier tests' bookings — not something this change touches or introduced.
Live manual verification in-browser: existing seeded customer sign-in via OTP; new customer registration via OTP (session created, landed on Home); installer wizard end-to-end through Step 3, confirming email-verification gating, Business Name pre-population from BUSINESS_NAME, and the read-only Booking URL / distinct Business Website fields.
All throwaway Docker containers/DBs used for this work have been removed; the real production database was never touched.
1. Card title fix: The "top-right text" feature was renamed and repositioned to be the actual card title (top-left, replacing the hardcoded "Loyalty Card"), matching what you asked for. This included a proper database migration (cardTopRightText → cardTitleText, etc., using CHANGE COLUMN so any already-configured value is preserved, not dropped) and updates through every layer — schema, service, owner form, and both the owner preview and customer-facing card. Verified live: typed "VIP Rewards" into the new "Card title" field and confirmed it renders top-left on both the owner's live preview and the real customer loyalty page, with the member number staying in its own badge top-right.
2. Tabs: The long "Card Appearance" control list is now split into Colours / Stamp / Text tabs (using the same Tabs component used elsewhere in the app), exactly as you suggested — Colours holds every colour + the background image, Stamp holds just the icon picker, Text holds the title, font, size, and terms line.
Along the way, while running full E2E regression, I found 6 test failures — but traced them via git stash to prove they're pre-existing bugs unrelated to this change (a booking/appointments-list bug), so I reverted-then-confirmed before restoring my work, and filed a separate follow-up task for them rather than mixing it into this change.
Both fixes are typechecked, linted, verified with the full unit (253) and integration (185) suites, confirmed live in a real browser end-to-end, and deployed to your running Docker container — the migration applied cleanly against your real database with no data loss.
Fixed an issue where media manager only shows files uploaded in specific sections.
Fixed an issue with icon picker names.
Removed jumbo rounding and a few other style tweaks.
Delivered:
Super Administrator — env-var provisioned, no StaffProfile at all (structural exclusion from Team/barber-picker/appointments/staff-totals, not a filter). hasPermission short-circuit + new getActingBusinessContext() helper retrofitted across 16 owner pages so it can actually manage the business.
Media Manager — one upload/library/external-URL modal + field picker, backing every image field app-wide. Local-disk storage + Docker volume, SVG rejected, size-capped.
Welcome backgrounds — desktop/mobile images with CSS breakpoint swap.
Business Branding settings — logo/cover/welcome/favicon/icon/colours all editable post-install; cover image finally rendered (was dead config).
Service descriptions — now surfaced on Home and in the booking flow.
Loyalty card — live preview, ColorPicker/MediaPicker/IconPicker, flip removed for a static premium-styled card, Loyalty added to bottom nav. Fixed a real pre-existing bug where the card's configured colour/image/icon were stored but never actually rendered.
Home Screen Redesign — hero gallery + sticky Services/Portfolio/Reviews/Details tabs, backed by a new unified gallery model/service (no hero/portfolio duplication). Details tab surfaces social links and a map that were never shown before.
Google Reviews — real sync pipeline (24h cron, CRON_SECRET-gated, mirrors the existing notification cron exactly), DB-only customer reads, owner hide/unhide + policy management page.
Architecture cleanup — SettingsPageShell extracted from 6 duplicated page wrappers; fixed a second pre-existing bug where branding image fields could never actually be cleared once set.
Verification: 418 tests passing (236 unit + 182 integration, all against a real MySQL database), full typecheck/lint clean across src, and a real Docker build+run cycle — which caught and fixed a genuine bug (scripts/ wasn't copied into the production image, so Super Admin sync would have crashed on every real deployment).
Owner Administration is complete. Summary of this final stretch of work:
Seed data extended with an inactive staff member, a pending invitation, a redeemed-reward fixture, a service with no eligible staff, and a future-appointment fixture for conflict testing — all idempotent, verified against the dev DB.
Testing brought to 179 unit / 86 integration / 27 E2E tests, all passing together on a freshly seeded, disposable Postgres:
Unit tests for every new pure validator (business hours, categories/services, booking rules, loyalty config, staff creation).
Integration tests covering opening-hours conflicts, last-owner protection, staff deactivation/eligibility conflicts, loyalty redemption's atomic race-guard, and owner-vs-barber/business-isolation authorization — all against a real Postgres.
12 new Playwright owner journeys, which surfaced and fixed two genuine issues along the way: a cookie-clearing race condition in the sign-out-mid-test flow (a real, reproducible timing bug, not just a test artifact), and confirmation that seed fixtures upserted by deterministic ID go stale once "today" has moved on — now handled defensively.
Desktop responsiveness: converted the single-column Business Details, Booking Rules, and Loyalty Configuration forms to a genuine two-column layout at the lg: breakpoint (verified via measured element positions, not just screenshots), confirmed mobile stacking is unaffected.
Final verification: clean tsc, eslint, and next build, plus the full three-suite run against one fresh database as the authoritative pass.
Phase 5 is complete. All 53 tasks are done, verified on a fresh database in a single clean run: **121 unit tests**, **55 integration tests**, and **15 E2E journeys** (6 Phase 4 + 9 new Phase 5) all passing, plus a clean `tsc`/`eslint`/`build`.
Summary of this final stretch:
- **Fixed a real bug**: `StaffService`'s break/time-off update/delete functions threw uncaught instead of failing gracefully on a permission mismatch — fixed with proper `PERMISSION_DENIED` handling, covered by new integration tests.
- **Built the remaining Phase 5 UI**: Breaks editor, Time Off editor, Barber Profile, and Notification Preferences — all wired to real services, no placeholders.
- **Extended seed data**: more customers, loyalty accounts/transactions/rewards, and appointments spanning every status today (anchored to real time so the "Current Appointment" priority logic is reliably exercised).
- **Found and fixed a second real bug live in the browser**: the Break/Time-Off edit sheets showed stale default values instead of the item being edited (a classic `useState`-doesn't-reinitialize-on-prop-change bug) — fixed with a `key` prop to force remount.
- **Wrote the full Phase 5 test suite**: unit tests for `selectCurrentAppointment` and all `StaffService` validators, integration tests for `LoyaltyService` and `StaffService` (including the permission-fix regression tests), and 9 new Playwright E2E journeys covering the brief's exact required list.
- **Did the desktop-responsive pass**: a persistent sidebar nav replacing the bottom bar at `lg:`, a genuine calendar+"Right Now" side-by-side split, and 2-column layouts for the clients list and customer details — addressing the brief's explicit "more than simple centering" requirement.
- **Wrote [docs/phase-5-summary.md](docs/phase-5-summary.md)** documenting everything above in full.
Nothing is committed — the whole session (Phases 2–5) sits uncommitted on top of the initial template commit, same as you left it. Let me know if you'd like me to commit, or if you want to move on to Phase 6.
Architecture: Six focused services with the BookingService/SchedulingService overlap resolved by giving SchedulingService exactly one job, the transactional double-booking guard , while BookingService owns the create/reschedule/cancel workflow around it.
59 unit tests, 24 integration tests
Base app architecture:
Route groups for customer, staff and owner.
* Reusable design system with around 20 UI components.
* Complete Prisma schema.
* Authentication with email/password and Google.
* Role and permission model.
* Protected routes.
* Clean separation between features, services, components and shared utilities.
Stefan Lazic